#token savings
Codemap — Local Code Graph
ThisaraPramu
Local-first code graph for chat: a privacy-audited @codegraph chat participant, interactive graph viewer, multi-language indexing, and slash commands for path/impact/report. Works with GitHub Copilot Chat.
TokenSaver
maazizit
Compress AI shell output automatically — no TokViz install needed. Bundles TokViz, detects Cursor/Copilot/Gemini-Antigravity, installs hooks silently. Dashboard shows tokens saved. Unlike TokGuess (usage tracking), this actually reduces context sent to your agent.
Tokengram
tokengram
Token-saving memory layer for Claude Code — hybrid RAG search over your project (local; up to 70% on search/Read-heavy tasks, less on edit-heavy refactors).
Badgr Auto — Token Optimization, Smart Routing, Local Models & Receipts
aibadgr
Cut AI coding costs with token optimization — strip repeated context on every request. Then route across local models, cheaper cloud tiers, and premium fallbacks. Track savings, latency, and receipts in VS Code.